4 papers
Efficient RL Training for LLMs with Experience Replay
Charles Arnal, Vivien Cabannes, Taco Cohen +2
While Experience Replay - the practice of storing rollouts and reusing them multiple times during training - is a foundational technique in general RL, it remains largely unexplore…
Automatic Textbook Formalization
Fabian Gloeckle, Ahmad Rammal, Charles Arnal +4
We present a case study where an automatic AI system formalizes a textbook with more than 500 pages of graduate-level algebraic combinatorics to Lean. The resulting formalization r…
The distance function to a finite set is a topological Morse function
Charles Arnal
In this short note, we show that the distance function to any finite set is a topological Morse function, regardless of whether is in general position.…
Mode Estimation with Partial Feedback
Charles Arnal, Vivien Cabannes, Vianney Perchet
The combination of lightly supervised pre-training and online fine-tuning has played a key role in recent AI developments. These new learning pipelines call for new theoretical fra…